Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say readOnlyHint=false, openWorldHint=false, destructiveHint=false, which is thin. The description compensates with rich behavioral detail: the server filters men's/women's apparel lines, searches each want only in category-matched stores, returns choiceSetId + pageUrl + catalogSearchScopeRu, and always requires sharing pageUrl in chat. It also exposes rendering constraints (canRenderImages=false for ChatGPT/Grok) and follow-up requirements, adding value far beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but every sentence carries operational weight: triggers, special cases, return values, mandatory sharing, and negative constraints. It is front-loaded with the core action, then the mandatory trigger, then domain-specific rules. There is no filler or repetition; the length is justified by the number of critical behaviors an agent must follow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, lack of output schema, and multiple domain rules, the description is remarkably complete. It covers triggers, parameter usage for alternatives and bundles, store scoping, apparel gender handling, return fields, follow-up with get_choice_status, and rendering/fallback constraints. An agent has everything needed to invoke the tool correctly in the intended scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 75%, the description materially enriches parameter understanding: it explains that kind=bundles is for basket/recipe contexts and that wants must include q for EVERY ingredient in one call. It also clarifies how canRenderImages should be set for certain model contexts and why agentIntroRu exists ('why you are asking, not choosing for them'). This is exactly the kind of semantic depth a schema cannot provide alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a comparison page (choice board, 2–4 options with pros/cons).' It clearly distinguishes present_choices from siblings like search_products and get_choice_status by naming its trigger and purpose. It is far from a tautology and gives an agent immediate understanding of what this tool produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use rules: 'MANDATORY when search_products returns 2+ similar hits or clarifyHint.action is present_choices — call immediately, do not wait for «сравни».' It also provides concrete when-not-to-use guidance: do not hand-pick SKUs from other stores, do not substitute a markdown table, and do not create_purchase until get_choice_status shows chosen or the owner picks in chat. This leaves no ambiguity about invocation timing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.